ParetoSlider conditions diffusion models on continuous preference weights to approximate the full Pareto front, providing dynamic control over multi-objective rewards at inference time.
hub
Flux.1 kontext: Flow matching for in-context image generation and editing in latent space,
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
representative citing papers
ChArtist generates pictorial charts via a Diffusion Transformer using skeleton-based spatial control and reference-image subject control, supported by a new 30,000-triplet dataset and data accuracy metric.
LooseRoPE modulates RoPE in diffusion attention maps to continuously trade off between preserving a pasted object's identity and harmonizing it with its new surroundings.
Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation.
MICo-150K is a new 150K-image dataset with 7 tasks, a De&Re real-image subset, MICo-Bench, and Weighted-Ref-VIEScore metric that improves AI models for generating consistent composites from arbitrary numbers of reference images.
The paper introduces a framework of four complementary analyses to evaluate the faithfulness of synthetic concept images from zero-shot T2I models versus real images for concept-based XAI.
Stepper uses stepwise panoramic expansion with a multi-view 360-degree diffusion model and geometry reconstruction to produce high-fidelity, structurally consistent immersive 3D scenes from text.
RenderFlow replaces iterative diffusion with flow matching for deterministic single-step neural rendering that achieves near real-time photorealistic quality and extends to inverse rendering via an adapter module.
Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.
The method warps pixels inside object boundaries with Snell's Law during generation and synchronizes with a second panorama image to produce optically plausible refraction in text-to-image outputs.
SkyReels-Text enables simultaneous fine-grained editing of multiple text regions in posters using arbitrary glyph patches for font control without labels or test-time fine-tuning.
GrOCE uses dynamic semantic graphs for online, training-free erasure of target concepts from diffusion model prompts via cluster identification and selective severing.
citing papers explorer
-
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control
ParetoSlider conditions diffusion models on continuous preference weights to approximate the full Pareto front, providing dynamic control over multi-objective rewards at inference time.
-
ChArtist: Generating Pictorial Charts with Unified Spatial and Subject Control
ChArtist generates pictorial charts via a Diffusion Transformer using skeleton-based spatial control and reference-image subject control, supported by a new 30,000-triplet dataset and data accuracy metric.
-
LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
LooseRoPE modulates RoPE in diffusion attention maps to continuously trade off between preserving a pasted object's identity and harmonizing it with its new surroundings.
-
Do-Undo Bench: Reversibility for Action Understanding in Image Generation
Do-Undo Bench is a new evaluation task and dataset that forces models to simulate forward action effects and then undo them to measure genuine action understanding in image generation.
-
MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
MICo-150K is a new 150K-image dataset with 7 tasks, a De&Re real-image subset, MICo-Bench, and Weighted-Ref-VIEScore metric that improves AI models for generating consistent composites from arbitrary numbers of reference images.
-
A Framework for Evaluating Zero-Shot Image Generation in Concept-based Explainability
The paper introduces a framework of four complementary analyses to evaluate the faithfulness of synthetic concept images from zero-shot T2I models versus real images for concept-based XAI.
-
Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas
Stepper uses stepwise panoramic expansion with a multi-view 360-degree diffusion model and geometry reconstruction to produce high-fidelity, structurally consistent immersive 3D scenes from text.
-
RenderFlow: Single-Step Neural Rendering via Flow Matching
RenderFlow replaces iterative diffusion with flow matching for deterministic single-step neural rendering that achieves near real-time photorealistic quality and extends to inverse rendering via an adapter module.
-
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
Scone unifies subject understanding and generation in a two-stage trained model to improve both composition and distinction in multi-subject image generation, outperforming prior open-source models on new benchmarks.
-
Refracting Reality: Generating Images with Realistic Transparent Objects
The method warps pixels inside object boundaries with Snell's Law during generation and synchronizes with a second panorama image to produce optically plausible refraction in text-to-image outputs.
-
SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design
SkyReels-Text enables simultaneous fine-grained editing of multiple text regions in posters using arbitrary glyph patches for font control without labels or test-time fine-tuning.
-
GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models
GrOCE uses dynamic semantic graphs for online, training-free erasure of target concepts from diffusion model prompts via cluster identification and selective severing.